Update README.md

README.md

@@ -23,10 +23,10 @@ It is a fine-tune of **Qwen 2.5-VL-7B** using ~10 k synthetic doc-to-Markdown pa
 
 *(note: the number of thinking tokens can vary from 20% to 2X the number of token of the final answers)*
 
----
+
 ## Results
 
-(we plan to realease a markdown arena -similar to llmArena- for complex document to markdown task)
+*(we plan to realease a markdown arena -similar to llmArena- for complex document to markdown task)*
 
 ### Arena ranking (using trueskill-2 ranking system)
 
@@ -53,7 +53,6 @@ It is a fine-tune of **Qwen 2.5-VL-7B** using ~10 k synthetic doc-to-Markdown pa
 
 GRPO model win 80% against model trained only with SFT
 
----
 
 ## Training